An Adaptive X-vector Model for Text-independent Speaker Verification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gu, Bin, Guo, Wu, Dai, Lirong, Du, Jun
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911323356397568
author Gu, Bin
Guo, Wu
Dai, Lirong
Du, Jun
author_facet Gu, Bin
Guo, Wu
Dai, Lirong
Du, Jun
contents In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding layers, where the parameters of the convolution filters are adjusted based on the input features. Compared with conventional CNNs, ACNNs have more flexibility in capturing speaker information. Moreover, we replace conventional batch normalization (BN) with adaptive batch normalization (ABN). By dynamically generating the scaling and shifting parameters in BN, ABN adapts models to the acoustic variability arising from various factors such as channel and environmental noises. Finally, we incorporate these two methods to further improve performance. Experiments are carried out on the speaker in the wild (SITW) and VOiCES databases. The results demonstrate that the proposed methods significantly outperform the original x-vector approach.
format Preprint
id arxiv_https___arxiv_org_abs_2002_06049
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle An Adaptive X-vector Model for Text-independent Speaker Verification
Gu, Bin
Guo, Wu
Dai, Lirong
Du, Jun
Audio and Speech Processing
Signal Processing
In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding layers, where the parameters of the convolution filters are adjusted based on the input features. Compared with conventional CNNs, ACNNs have more flexibility in capturing speaker information. Moreover, we replace conventional batch normalization (BN) with adaptive batch normalization (ABN). By dynamically generating the scaling and shifting parameters in BN, ABN adapts models to the acoustic variability arising from various factors such as channel and environmental noises. Finally, we incorporate these two methods to further improve performance. Experiments are carried out on the speaker in the wild (SITW) and VOiCES databases. The results demonstrate that the proposed methods significantly outperform the original x-vector approach.
title An Adaptive X-vector Model for Text-independent Speaker Verification
topic Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2002.06049